@HuggingPapers: NVIDIA just released AnyFlow on Hugging Face The first any-step video diffusion model that generates high-quality text-…
Summary
NVIDIA released AnyFlow, the first any-step video diffusion model for text-to-video generation, allowing smooth quality scaling across inference budgets (4 to 50 steps).
View Cached Full Text
Cached at: 05/13/26, 06:24 PM
NVIDIA just released AnyFlow on Hugging Face
The first any-step video diffusion model that generates high-quality text-to-video with any inference budget - 4 steps or 50, quality scales smoothly without degradation. https://t.co/bT6scg98ZT
Similar Articles
@HuggingPapers: NVIDIA just released an NVFP4-quantized DiffusionGemma on Hugging Face A 26B MoE multimodal model generating text via p…
NVIDIA released a 26B MoE multimodal model called DiffusionGemma on Hugging Face, using NVFP4 quantization and achieving over 1,100 tokens per second on Hopper hardware.
Fine-tune video and image models at scale with NVIDIA NeMo Automodel and 🤗 Diffusers
NVIDIA NeMo Automodel integrates with Hugging Face Diffusers to enable scalable distributed fine-tuning of diffusion models for image and video generation, supporting models like FLUX.1-dev, Wan 2.1, and HunyuanVideo.
Nvidia's New Long-Form Video Generation (12 minute read)
NVIDIA Research introduces SANA-Video 2.0, a hybrid video diffusion transformer that generates high-quality 720p video on a single GPU, achieving up to 120× speedup over Wan 2.2-14B via hybrid linear-softmax attention and block attention residuals.
AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation
AnyFlow introduces a novel any-step video diffusion distillation framework that optimizes full ODE sampling trajectories through flow-map transition learning and backward simulation, achieving performance that matches or surpasses consistency-based counterparts while scaling with sampling step budgets.
@jiqizhixin: What if you could generate high-quality images in one step instead of hundreds? Stanford and ByteDance introduce W-Flow…
Stanford and ByteDance introduce W-Flow, a single-step generative model that uses Wasserstein gradient flows to achieve state-of-the-art one-step ImageNet 256x256 generation (1.29 FID) with 100x faster sampling than multi-step diffusion models.